Type with your Voice.
MacOS app that makes typing effortless. Get text out of your head into any app using just your voice.
AI Agents
Chat with Claude, ChatGPT, Gemini, and more
Free with your OpenRouter API key. No credit card required.
Type faster than 99%
120-150 WPM is your natural speaking speed.
Top 1% best typists average 100 WMP. Instantly outpace 99% of population by typing with your voice.
Zero cognitive load
You've been speaking since age two. It feels automatic. Typing demands focus. Every typo breaks flow. Speaking leaves your mind free to solve the actual problem.
Better AI results
When input is effortless, you don't trim details. You naturally include every nuance. That extra context is what makes your AI agent work on the first shot.
What describes you better?
Feel mental fatigue after a day of prompting AI agents?
See how we compare
Pay-per-use pricing. Your own API key. Full control over your data and models.
| Feature | Ottex | Wispr Flow | Aqua Voice | Willow |
|---|---|---|---|---|
| Pricing | ~$1-3/mo (BYOK) | $15/mo | $10/mo | $15/mo |
| Privacy (we never see your data) | ||||
| Not used for AI training | ||||
| AI Shortcuts (select + process) | ||||
| Model flexibility (not locked in) | Gemini, Mistral, Whisper, etc. | |||
| Snippets (text expansion) | ||||
| Custom dictionary | ||||
| Custom instructions | ||||
| Smart formatting | ||||
| Transcription history | ||||
| Latency - short audio (10 sec) | 1-2s | 0.5-1s | 0.5-1s | 0.5-1s |
| Latency - long audio (2 min) | 3-5s | 3-5s | 2-3s | 3-4s |
| Memory footprint | ~50-150 MB (native) | ~575 MB (Electron) | ~250 MB (Electron) | ~50-150 MB (native) |
| Feature | Ottex | Wispr Flow | Aqua Voice | Willow |
|---|---|---|---|---|
| Pricing | ~$1-3/mo (BYOK) | $15/mo | $10/mo | $15/mo |
| Privacy (we never see your data) | ||||
| Not used for AI training | ||||
| AI Shortcuts (select + process) | ||||
| Model flexibility (not locked in) | Gemini, Mistral, Whisper, etc. | |||
| Snippets (text expansion) | ||||
| Custom dictionary | ||||
| Custom instructions | ||||
| Smart formatting | ||||
| Transcription history | ||||
| Latency - short audio (10 sec) | 1-2s | 0.5-1s | 0.5-1s | 0.5-1s |
| Latency - long audio (2 min) | 3-5s | 3-5s | 2-3s | 3-4s |
| Memory footprint | ~50-150 MB (native) | ~575 MB (Electron) | ~250 MB (Electron) | ~50-150 MB (native) |
Simple, transparent pricing
Free for personal use. Enterprise pricing for teams who want to connect their own AI infrastructure.
What's included:
What's included:
Your data stays on your device
We built Ottex with a simple principle: your words are yours
No data collection
We don't collect, store, or analyze your transcriptions. Your voice recordings are processed and immediately discarded.
Invisible to us
Your AI conversations go directly to your chosen provider. We never see, log, or have access to your prompts or responses.
Your keys, your control
API keys are stored locally in your macOS Keychain. They never touch our servers—we literally can't access them.
We don't train models on your data
Your AI requests are never used (by us) to train AI models. Check the policies of your chosen AI provider for details.
Ready to think at full bandwidth?
Free with your OpenRouter API key. Start speaking in under a minute.
No credit card required.